DeepInfra vs Jais 3

DeepInfra

The model list, context sizes and per-token prices are readable without a key, and keys can carry an IP allowlist, a monthly spending cap and model-limited JWTs. Deprecated models get one week's notice and are then redirected to another model, there is no changelog or SLA, and an account needs a card or prepayment before any call.

Jais 3

Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code, and no technical report or security contact is published.

DeepInfra

1. Call GET https://api.deepinfra.com/v1/openai/models at start-up for ids, context sizes and prices. No key is needed
2. Check the model field of each response. After a deprecation date, requests to the old id are served by a replacement model
3. Ask the account owner for a scoped JWT limited to the models and spend the task needs, not the full API key
4. Stay under 200 concurrent requests per model. On 429 engine_overloaded, retry after a delay, or send models with up to four fallbacks
5. Never inspect a JWT with GET /v1/scoped-jwt?jwtoken=, which puts the token in the URL. Keep credentials in the Authorization header

Jais 3

1. Start vLLM or SGLang with --reasoning-parser k2_horizon, and add --tool-call-parser k2_horizon (vLLM also --enable-auto-tool-choice) for tools, or tool calls come back as raw text
2. Pass reasoning_effort (high, medium or low) and tool_call_format inside chat_template_kwargs. Other values return a template error
3. Send each earlier assistant turn back with reasoning_content as a string, even an empty one. A missing or null thinking field makes the template raise an error
4. Send your own system message, or set default_system_prompt to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras
5. Budget at least 32,768 output tokens at high effort, which the cards recommend for every request